From 8764ed55c9705e426d889ff16c26f398bba70b9b Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Mon, 29 Apr 2019 07:04:15 -0700 Subject: KVM: x86: Whitelist port 0x7e for pre-incrementing %rip KVM's recent bug fix to update %rip after emulating I/O broke userspace that relied on the previous behavior of incrementing %rip prior to exiting to userspace. When running a Windows XP guest on AMD hardware, Qemu may patch "OUT 0x7E" instructions in reaction to the OUT itself. Because KVM's old behavior was to increment %rip before exiting to userspace to handle the I/O, Qemu manually adjusted %rip to account for the OUT instruction. Arguably this is a userspace bug as KVM requires userspace to re-enter the kernel to complete instruction emulation before taking any other actions. That being said, this is a bit of a grey area and breaking userspace that has worked for many years is bad. Pre-increment %rip on OUT to port 0x7e before exiting to userspace to hack around the issue. Fixes: 45def77ebf79e ("KVM: x86: update %rip after emulating IO") Reported-by: Simon Becherer Reported-and-tested-by: Iakov Karpov Reported-by: Gabriele Balducci Reported-by: Antti Antinoja Cc: stable@vger.kernel.org Cc: Takashi Iwai Cc: Jiri Slaby Cc: Greg Kroah-Hartman Signed-off-by: Sean Christopherson Signed-off-by: Paolo Bonzini --- arch/x86/include/uapi/asm/kvm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/x86/include') diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index dabfcf7c3941..7a0e64ccd6ff 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -381,6 +381,7 @@ struct kvm_sync_regs { #define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0) #define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1) #define KVM_X86_QUIRK_LAPIC_MMIO_HOLE (1 << 2) +#define KVM_X86_QUIRK_OUT_7E_INC_RIP (1 << 3) #define KVM_STATE_NESTED_GUEST_MODE 0x00000001 #define KVM_STATE_NESTED_RUN_PENDING 0x00000002 -- cgit v1.2.3 From 0699c64a4be6e4a6137240379a1f82c752e663d8 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Tue, 30 Apr 2019 19:33:26 +0200 Subject: x86/kvm/mmu: reset MMU context when 32-bit guest switches PAE Commit 47c42e6b4192 ("KVM: x86: fix handling of role.cr4_pae and rename it to 'gpte_size'") introduced a regression: 32-bit PAE guests stopped working. The issue appears to be: when guest switches (enables) PAE we need to re-initialize MMU context (set context->root_level, do reset_rsvds_bits_mask(), ...) but init_kvm_tdp_mmu() doesn't do that because we threw away is_pae(vcpu) flag from mmu role. Restore it to kvm_mmu_extended_role (as we now don't need it in base role) to fix the issue. Fixes: 47c42e6b4192 ("KVM: x86: fix handling of role.cr4_pae and rename it to 'gpte_size'") Signed-off-by: Vitaly Kuznetsov Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/mmu.c | 1 + 2 files changed, 2 insertions(+) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index a9d03af34030..c79abe7ca093 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -295,6 +295,7 @@ union kvm_mmu_extended_role { unsigned int valid:1; unsigned int execonly:1; unsigned int cr0_pg:1; + unsigned int cr4_pae:1; unsigned int cr4_pse:1; unsigned int cr4_pke:1; unsigned int cr4_smap:1; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index e10962dfc203..d9c7b45d231f 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -4781,6 +4781,7 @@ static union kvm_mmu_extended_role kvm_calc_mmu_role_ext(struct kvm_vcpu *vcpu) union kvm_mmu_extended_role ext = {0}; ext.cr0_pg = !!is_paging(vcpu); + ext.cr4_pae = !!is_pae(vcpu); ext.cr4_smep = !!kvm_read_cr4_bits(vcpu, X86_CR4_SMEP); ext.cr4_smap = !!kvm_read_cr4_bits(vcpu, X86_CR4_SMAP); ext.cr4_pse = !!is_pse(vcpu); -- cgit v1.2.3